2.1 Linguistic Inquiry and Word Coun

Word classification used the Linguistic Inquiry and Word Count 2015 (LIWC) dictionary (Pennebaker et al., 2015) and tokenising tools from the Quanteda R package (Benoit, 2018). Word counts and words-per-sentence were calculated using stringi (Gagolewski, 2018), a wrapper to the ICU regex library.

Following Yu (2014) drawing on Newman, Groom, Handelman, & Pennebaker (2008) we used the following LIWC categories:

• All Pronouns (pronoun)
• First person singular pronouns (i)
• First person plural pronouns (we)
• Verbs (verb)
• Auxiliary verbs (auxverb)
• Social processes (social)
• Positive emotions (posemo)
• Negative emotions (negemo)
• Tentative words (tentat)
• Articles (article)
• Prepositions (preps)
• Anger words (anger)
• Swear words (swear)
• Cognitive processes (cogproc)
• Words longer than six letters (Sixltr)

We also included mean words-per-sentence (WPS), total speach word count (WC) and Flesch–Kincaid grade level (FK) (Kincaid, Fishburne, Rogers, & Chissom, 1975), calculated using Quanteda (Benoit, 2018) and stringi (Gagolewski, 2018).

2.2 Women vs Men

There are no categories where gender differences meet the effect size threshold of \(|0.2|\) suggested by Cohen (1988, pp. 25–26) to indicate a small effect. 4 categories – words with more than six letters, prepositions, words-per-sentence and Flesh-Kincaid grade level – exceeded the \(|0.1|\) threshold suggested by Newman et al (2008).

2.3 Short lists vs Non-Short lists

The following plots show changes in the occurences of selected LIWC terms, words-per-sentence, total word count and Flesch–Kincaid grade level, over the course of an MP’s career. There do not appear to be any notable changes in speaking style over the course of female Labour MPs’ careers.

Occurence of selected LIWC terms

There are no categories among female Labour MPs by selection process meeting the \(|0.2|\) threshold. Only one category – first person plural pronouns, d=0.19 – exceeded \(|0.1|\).

2.4 Conservatives vs Labour

There are no categories with effect sizes exceeding \(|0.2|\) between Labour and Conservative MPs, like inter-Labour differences.

2.5 All MPs Gender Differences

There are no categories with effect sizes exceeding \(|0.2|\) when comparing all male and female MPs elected from 1997 onwards. There is only one category, “Articles”, with an effect size of 0.11, greater than the \(|0.1|\) threshold suggested by Newman et al. (2008).

2.6 POS Analysis

Part-of-speech (POS) tagging was done using spaCy (Honnibal & Montani, 2017) and the spacyr package (Benoit & Matsuo, 2018). There is one small gender difference (d = \(|0.22|\)) in the use of plural nouns, which make up 5.85% of the words used by female Labour MPs, compared to 5.03% of words spoken by male Labour MPs. As with LIWC, there are no categories where d >= \(|0.2|\) when comparing female Labour MPs by selection process.

2.7 Tokenising / Keyness

The most commonly used words by both men and women would be protocol decorum expressions, so we calculate the keyness of words to identify gender differences in the choices of topics raised by men and women, and by short-list and non-short list women.

2.7.1 Men vs Women

Keyness – a linguistic measure of the frequency of different words in two groups of texts – reveals clear gender differences in the most disproportionately common words used by female and male Labour MPs. Unsurprisingly, despite male MPs saying almost twice as many words (30,596,921 vs 15,897,929) as their female colleagues, female Labour MPs were more than two-and-a-half (2.61) times as likely to say “women”. They were also much more likely to use “women’s” and “woman” in parliamentary debate. Female Labour MPs also appear much more likely to discuss “children”, “people”, “care”, “families”, “home”, “parents”, “work” and social policy areas such as “services”, “disabled [people]” and “housing” than their male colleagues. Male MPs were more likely to refer to military topics (“Iraq”, “nuclear”), and to parliamentary process and protocol – “question”, “political”, “conservative”, “electoral”, “house”, “party”, “argument” “liberal” and “point” are far more common in speeches by male Labour MPs than by female ones. This could suggest that male Labour MPs are more comfortable using the traditional language of House of Commons debate, and are more concerned with the rules, procedures and processes of the parliamentary system than their female colleagues.

Keyness between Labour MPs, by Gender

2.7.2 Short lists vs Non-Short lists

Keyness differences by selection process are not as obviously stereotypical. Nonetheless, the most common words amongst AWS MPs included “carers”, “disabled”, “bedroom” and “sen”². Also of note is AWS MPs making more references to their “constituency” and its “constituents”, suggesting that AWS MPs may draw on the fact they were elected by their constituents as a source political legitimacy, at least more than non-AWS MPs.

Keyness between Female Labour MPs, by Selection Process

2.7.3 Labour vs Conservative

The keyness differences between Labour and Conservative MPs are much greater than gender differences within Labour. The very high use of “Lady” by Conservative MPs is reflective of the greater proportion of female MPs in other parties, as it is often used to refer to comments by other members of the house. It may also represent a greater use of traditional hosue decorum by Conservative MPs.

Keyness between Labour and Conservative MPs

2.8 Bigrams

We created bigrams of all first person plural and singular pronouns for female Labour MPs. As above, AWS MPs are far more likely to make references to their constituency or their constituents.

Bigram Keyness in Female Labour MPs by Selection Process

2.9 Naive Bayes classification

We trained a Naive Bayes classifier with document-frequency priors and a multinomial distribution to predict the gender of speakers when given speeches by all Labour MPs in our dataset, and the selection process when only given female Labour MPs. The accuracy of both models were roughly equivalent, 70.55% accuracy when predicting gender and 70.84% when predicting short lists. By contrast, the classifier could distinguish between Labour and Conservative speeches with 74.23% accuracy.

2.10 Topic Models

Using topic models to classify text is widely used in social sciences (Grimmer & Stewart, 2013), as, when combined with the large volume of plain text data available, it allows for a rapid and consistent method of analysis . Topic modelling and other statistic methods of textual analysis are not a substitute for reading the texts themselves, but can augment other analysis or – as in this case – analyse and classify larger amounts of text than would be feasible using human coders (Grimmer & Stewart, 2013). Topic models classify a series of documents (in this case individual speeches) into one of a given number of topics, identifying terms that are common in some documents but rare in others. When developing topic models, there is a trade-off between high precision in the classification of each document with broader topics when using smaller numbers of topics, or lower precision in individual speech classification with more finely-grained topics when using larger numbers of topics. Grimmer & Stewart (2013) also highlight the importance of validating unsurpervised topic models when applied to new sets of texts.

The R package stm (Roberts, Stewart, & Tingley, 2018) implements a structured topic model (STM) (Arora et al., 2013; Roberts, Stewart, & Airoldi, 2016). An STM incorporates data about the writer or speaker into the topic classification algorithm. This differs from traditional topic modelling methods using latent variables to identify topics (e.g. with latent Dirichlet allocation Blei, Ng, & Jordan, 2003), and then comparing proportions of each topic to one or more external variables. STM allows us to incorporate the variables we are interested in to the topic model itself, i.e. the proportion of speechs classified as belonging to each topic can vary as a function of the AWS variable.

We incorporated the AWS status of speakers into our topic model, using all speeches by female Labour MPs, with their AWS status as a covariate in classifying topics. We then matched these topics to speechs by male Labour MPs.

We produced two different structured topic model implementations, with different numbers of topics (K).

The first implementation used an algorithm developed by Lee & Mimno (2014), implemented in the stm package (Roberts et al., 2018), to estimate the number of topics across all speeches made by female Labour MPs, using the “spectral” method developed by Arora et al. (2013), implemented by Roberts et al. (2018). The resulting topic model has 69 topics, across 81,607 documents and a dictionary of 115,477 words. However, the topic quality with K = 69 is poor, and several topics have poor semantic coherence (see , and the appendix).

2.10.1 Short lists vs Non-Short lists - K30

As seen in the word lists in the appendix, there is relatively scattershot semantic coherence, although exclusivity is high, when using the 69 topic models suggested by Lee and Mimno’s (2014) algorithm. We therefore re-ran the analysis, using 30 topic models, which resulted in increased semantic coherence, albeit with slightly lower exclusivity, as illustrated in Figure . The lower number of models also makes accurate hand-coding of topics possible.

We created a Fruchterman-Reingold (Fruchterman & Reingold, 1991) diagram to show the connections between different topics. Larger vertices indicate more common topics, and the plot uses a colour scale to indicate the proportion of speeches classed in that topic made by AWS and non-AWS female Labour MPs. The space between vertices indicate the closeness of two topics.

Fruchterman-Reingold plot of K30 Network

Coherence of K30 Topic Models

The stm package includes the estimateEffect function to create a regression model using individual documents (speeches) as individual observations, with the number of documents fitting each topic as the dependent variable and model covariates (AWS status) as independent variables.

In all but five topics (gender, immigration, international, children and the environment) the model found p values of < 0.01, and in every topic except the aforemention and “people”, p values of < 0.001.

Topic Estimates

	Estimate	Standard Error	t value	Pr(>|t|)
Topic 1 – Bills
Intercept	0.0449633	0.0006498	69.1927133	< 0.001	***
Short List	-0.0068652	0.0008157	-8.4158760	< 0.001	***
Topic 2 – Consultations
Intercept	0.0757456	0.0006088	124.4135491	< 0.001	***
Short List	-0.0214950	0.0007211	-29.8072043	< 0.001	***
Topic 3 – Gender
Intercept	0.0230188	0.0006054	38.0240848	< 0.001	***
Short List	-0.0007313	0.0006927	-1.0557346	0.29
Topic 4 – Police
Intercept	0.0289330	0.0006350	45.5645109	< 0.001	***
Short List	-0.0074441	0.0007453	-9.9881995	< 0.001	***
Topic 5 – European Union
Intercept	0.0368405	0.0006729	54.7504749	< 0.001	***
Short List	-0.0050989	0.0007784	-6.5507532	< 0.001	***
Topic 6 – Transport
Intercept	0.0218012	0.0005744	37.9563742	< 0.001	***
Short List	0.0054380	0.0007675	7.0850991	< 0.001	***
Topic 7 – Disability
Intercept	0.0298360	0.0006461	46.1800470	< 0.001	***
Short List	0.0131765	0.0007849	16.7879674	< 0.001	***
Topic 8 – Immigration
Intercept	0.0186039	0.0004805	38.7189859	< 0.001	***
Short List	0.0004577	0.0006259	0.7313654	0.46
Topic 9 – Disease
Intercept	0.0249569	0.0005888	42.3893263	< 0.001	***
Short List	-0.0051127	0.0007222	-7.0788362	< 0.001	***
Topic 10 – Parties
Intercept	0.0378846	0.0004751	79.7467610	< 0.001	***
Short List	0.0020066	0.0005987	3.3514073	< 0.001	***
Topic 11 – Health Care
Intercept	0.0407905	0.0006961	58.5999064	< 0.001	***
Short List	-0.0083156	0.0008737	-9.5180094	< 0.001	***
Topic 12 – Members
Intercept	0.0389968	0.0005993	65.0713124	< 0.001	***
Short List	0.0082184	0.0007302	11.2551023	< 0.001	***
Topic 13 – Investment
Intercept	0.0302313	0.0006154	49.1261500	< 0.001	***
Short List	-0.0028620	0.0007741	-3.6972528	< 0.001	***
Topic 14 – Crime
Intercept	0.0239303	0.0005292	45.2214465	< 0.001	***
Short List	-0.0032121	0.0006371	-5.0418257	< 0.001	***
Topic 15 – Justice
Intercept	0.0409423	0.0006878	59.5228004	< 0.001	***
Short List	-0.0167466	0.0008429	-19.8683165	< 0.001	***
Topic 16 – Energy
Intercept	0.0384171	0.0006743	56.9719478	< 0.001	***
Short List	-0.0046100	0.0008719	-5.2874762	< 0.001	***
Topic 17 – People
Intercept	0.0788563	0.0005752	137.0944198	< 0.001	***
Short List	0.0019922	0.0007230	2.7555854	0.006	**
Topic 18 – Education
Intercept	0.0298510	0.0006842	43.6284617	< 0.001	***
Short List	0.0038047	0.0008443	4.5061502	< 0.001	***
Topic 19 – Fishing
Intercept	0.0196069	0.0004960	39.5281208	< 0.001	***
Short List	0.0092594	0.0006585	14.0621858	< 0.001	***
Topic 20 – Housing
Intercept	0.0204434	0.0005486	37.2667515	< 0.001	***
Short List	0.0038473	0.0007514	5.1199139	< 0.001	***
Topic 21 – Tax & Budgets
Intercept	0.0460797	0.0007993	57.6466588	< 0.001	***
Short List	0.0142945	0.0010081	14.1799697	< 0.001	***
Topic 22 – Farmers
Intercept	0.0139625	0.0004691	29.7626596	< 0.001	***
Short List	0.0055240	0.0005797	9.5290003	< 0.001	***
Topic 23 – International
Intercept	0.0261568	0.0006786	38.5431264	< 0.001	***
Short List	0.0007715	0.0008471	0.9108196	0.36
Topic 24 – Media
Intercept	0.0124115	0.0003960	31.3427056	< 0.001	***
Short List	0.0048964	0.0004979	9.8338502	< 0.001	***
Topic 25 – Local authorities
Intercept	0.0426114	0.0006104	69.8123561	< 0.001	***
Short List	-0.0085925	0.0007381	-11.6415862	< 0.001	***
Topic 26 – Children
Intercept	0.0250044	0.0005685	43.9835308	< 0.001	***
Short List	-0.0000121	0.0007339	-0.0164345	0.99
Topic 27 – Environment
Intercept	0.0149434	0.0004799	31.1365480	< 0.001	***
Short List	0.0003248	0.0005945	0.5463792	0.58
Topic 28 – Ministers
Intercept	0.0427008	0.0005833	73.2084634	< 0.001	***
Short List	0.0145502	0.0007220	20.1539326	< 0.001	***
Topic 29 – Parliament
Intercept	0.0187969	0.0005246	35.8334273	< 0.001	***
Short List	0.0063043	0.0006868	9.1788680	< 0.001	***
Topic 30 – Other
Intercept	0.0526683	0.0003251	161.9821372	< 0.001	***
Short List	-0.0037495	0.0003943	-9.5080507	< 0.001	***

Count and Distribution of Topics – K30

Topic Number	AWS Speeches	Percent of AWS Speeches	Non-AWS Speeches	Percent of non-AWS Speeches	Male MP Speeches	Percent of Male MP Speeches
Topic 1	1,792	3.34%	1,229	4.4%	8,163	4.82%
Topic 2	2,476	4.61%	2,514	9.01%	11,392	6.73%
Topic 3	1,082	2.01%	632	2.27%	926	0.55%
Topic 4	1,303	2.43%	900	3.23%	3,364	1.99%
Topic 5	1,976	3.68%	1,371	4.91%	9,653	5.7%
Topic 6	1,720	3.2%	623	2.23%	4,562	2.69%
Topic 7	2,721	5.07%	758	2.72%	4,045	2.39%
Topic 8	879	1.64%	381	1.37%	2,192	1.29%
Topic 9	1,008	1.88%	743	2.66%	1,747	1.03%
Topic 10	1,351	2.52%	658	2.36%	6,235	3.68%
Topic 11	2,144	3.99%	1,552	5.56%	4,494	2.65%
Topic 12	2,507	4.67%	883	3.16%	10,395	6.14%
Topic 13	1,231	2.29%	825	2.96%	3,972	2.35%
Topic 14	984	1.83%	646	2.32%	1,570	0.93%
Topic 15	1,180	2.2%	1,410	5.05%	4,935	2.91%
Topic 16	2,175	4.05%	1,302	4.67%	7,547	4.46%
Topic 17	5,309	9.89%	2,357	8.45%	25,255	14.91%
Topic 18	2,362	4.4%	1,003	3.59%	6,230	3.68%
Topic 19	1,183	2.2%	445	1.59%	3,305	1.95%
Topic 20	1,334	2.48%	561	2.01%	2,075	1.23%
Topic 21	4,361	8.12%	1,556	5.58%	11,845	6.99%
Topic 22	977	1.82%	359	1.29%	2,259	1.33%
Topic 23	1,787	3.33%	890	3.19%	6,124	3.62%
Topic 24	813	1.51%	233	0.84%	2,132	1.26%
Topic 25	1,604	2.99%	1,104	3.96%	4,917	2.9%
Topic 26	1,237	2.3%	664	2.38%	1,105	0.65%
Topic 27	668	1.24%	325	1.16%	1,796	1.06%
Topic 28	3,218	5.99%	1,001	3.59%	8,906	5.26%
Topic 29	1,121	2.09%	304	1.09%	4,463	2.64%
Topic 30	1,202	2.24%	673	2.41%	3,746	2.21%

K30 Pyramid Chart

K30 Bar Chart

AWS are – proportionally – more likely than non-AWS MPs to discuss Topics 29 (parliament), 7 (disability) and 24 (media). They are proportionally less likely to mention Topics 15 (justice), 2 (consultations) and 9 (disease). See Figure for more details. Perhaps surprisingly, AWS MPs are slightly less likely to mention gender issues (Topic 3), although the difference is not statistically significant (see the appendix for details).

K30 Topic Proportions

2.10.1.1 Word Occurences

Words in Topic - K30

Topic Number	Top Ten Words	Top Ten FREX
Topic 1	bill, amendment, clause, new, legislation, amendments, act, committee, provisions, 1	amendment, clause, amendments, clauses, nos, insert, subsection, provisions, bill, tabled
Topic 2	issues, public, information, also, report, review, process, work, need, important	consultation, review, guidance, recommendations, information, considering, decisions, arrangements, framework, detailed
Topic 3	women, men, pay, equality, rights, women’s, discrimination, equal, work, woman	women, equality, gender, equalities, bishops, discrimination, female, women’s, equal, men
Topic 4	police, crime, officers, behaviour, policing, home, antisocial, community, work, force	policing, antisocial, constable, burglary, wardens, crime, constabulary, police, officers, pcsos
Topic 5	european, uk, countries, eu, union, trade, international, united, world, british	treaty, enlargement, wto, lisbon, doha, eu, eu’s, mod, multilateral, accession
Topic 6	transport, london, rail, bus, road, services, line, travel, network, train	rail, bus, passengers, fares, trains, buses, passenger, heathrow, congestion, hs2
Topic 7	people, work, benefit, pension, benefits, support, disabled, employment, carers, working	disabled, jobcentre, incapacity, carers, pension, claimants, esa, dla, pensions, atos
Topic 8	immigration, safety, uk, asylum, enforcement, home, number, illegal, licensing, animals	dogs, dog, id, visa, fur, mink, hse, sia, seekers, fireworks
Topic 9	health, research, cancer, treatment, medical, disease, can, smoking, patients, people	cancer, diseases, vaccine, flu, embryos, infections, diabetes, palliative, prostate, cervical
Topic 10	government, labour, conservative, party, opposition, policy, government’s, scotland, scottish, members	conservative, liberal, democrats, conservatives, scottish, democrat, scotland, tory, interruption, tories
Topic 11	care, health, nhs, services, service, hospital, patients, staff, trust, social	dentists, ambulance, dentistry, helier, dentist, nurses, hospital, pct, hospitals, dental
Topic 12	member, members, debate, house, mr, committee, said, time, speaker, north	member, speaker, mr, debate, spoke, thoughtful, backbench, debates, madam, select
Topic 13	companies, financial, company, market, scheme, money, debt, consumers, bank, credit	payday, annuity, oft, policyholders, penrose, fca, loan, prepayment, loans, annuities
Topic 14	young, people, health, mental, youth, prison, problems, drugs, alcohol, drug	prisons, probation, cannabis, reoffending, mental, prison, self-harm, youth, alcohol, sentences
Topic 15	cases, court, legal, law, case, justice, evidence, criminal, courts, home	judicial, attorney-general, defendant, extradition, tpims, suspects, court, courts, prosecution, isc
Topic 16	energy, businesses, business, jobs, investment, economy, industry, economic, new, sector	carbon, renewable, renewables, solar, low-carbon, energy, feed-in, manufacturing, steel, businesses
Topic 17	people, want, one, get, know, say, us, many, think, need	things, think, something, get, want, going, really, say, lot, go
Topic 18	education, schools, school, children, training, skills, parents, teachers, students, young	schools, teachers, pupils, curriculum, sen, academies, ofsted, pupil, grammar, attainment
Topic 19	constituency, city, people, many, years, work, centre, one, hull, great	fishermen, cod, hull, plymouth, maiden, fishing, fish, humber, fleetwood, tourism
Topic 20	housing, homes, people, private, london, social, home, affordable, need, accommodation	rent, tenants, landlords, rented, homelessness, homeless, rents, tenancies, housing, tenancy
Topic 21	tax, year, million, government, budget, cuts, cut, poverty, increase, billion	tax, obr, vat, millionaires, 50p, inflation, budget, fiscal, chancellor, cut
Topic 22	food, post, office, rural, petition, offices, farmers, royal, mail, government	petition, farmers, petitioners, meat, cull, labelling, cattle, badger, culling, beef
Topic 23	people, international, human, government, war, rights, country, un, conflict, world	syria, israel, civilians, palestinian, israeli, gaza, sri, holocaust, hatred, sierra
Topic 24	bbc, media, online, internet, sport, access, digital, culture, clubs, football	bbc, games, olympic, gambling, bbc’s, copyright, lap-dancing, broadband, radio, internet
Topic 25	local, authorities, funding, areas, services, council, community, authority, government, communities	local, authorities, funding, councils, grant, authority, formula, deprived, areas, partnership
Topic 26	children, child, families, care, family, parents, violence, support, domestic, victims	trafficked, csa, same-sex, adopters, child, rape, marriages, marriage, sexual, couples
Topic 27	planning, water, development, land, environment, site, sites, flood, environmental, area	forestry, biodiversity, masts, habitats, gypsy, flood, waterways, flooding, marine, mmo
Topic 28	secretary, state, house, last, statement, report, said, now, question, answer	secretary, statement, state, confirm, official, answer, vol, state’s, letter, written
Topic 29	parliament, wales, vote, commission, political, assembly, people, welsh, elected, charities	electoral, polling, gibraltar, voting, assembly, vote, votes, voter, ballot, elections
Topic 30	can, make, ensure, agree, important, take, made, point, sure, welcome	agree, aware, sure, ensure, taking, lady, welcome, steps, point, make

2.11 Discussion

There do not appear to be substantial or meaningful differences in the speaking styles of female Labour MPs selected through all women short lists when compared to their female colleagues selected through open short lists using LIWC. This is possibly due to the speaking style dominant in British parliamentary debate, which is more formal than the speech used in most day-to-day conversation. LIWC has American developers, and the dictionary may not be able to capture stylistic differences between American and British English, and may not include words commonly used in formal British English speech, limiting its usefulness in a British context.

There is more gender distinction in some selected terms and topics. AWS MPs are far more likely to make reference to their constituency and their constituents. In the debate between whether MPs should be “delegates” or “trustees” – the “mandate-independence controversy” outlined by Pitkin (1967) – the references to their constituents and constituencies suggests AWS MPs shy away from the Burkean concept of trusteeship and see themselves more as strict representatives of their constituents. In Andeweg & Thomassen’s (2005) typology of ex ante/ex post and above/below political representation, AWS MPs lean towards representation “from below”, although their selection process is ex ante/ex post.

AWS MPs refer to their constituents both specifically and in the abstract, particularly when criticising government policy. For example, in debate on 4th March 2015, Gemma Doyle, than the Labour MP for West Dunbartonshire (elected on an AWS in 2010), when asked if she would give way to Conservative MP Stephen Mosley, responded:

No, I will not [give way], because my constituents want me to make these points, not to give more time to Conservative Members.

On 2nd June 2010, during debate on Israel-Palestine, Valerie Vaz, MP for Walsall South:

My constituents want more than pressure. Will the Foreign Secretary come back to the House and report on a timetable for the discussions on a diplomatic solution, just as we did on Ireland?

On 4th April 2001, Betty Williams, member for Conwy from 1997–2010, raised the case of a wilderness guide in her constituency unable to access parts of the countryside due to foot and mouth disease:

Is my right hon. Friend aware that there is continuing concern about the limited access to the countryside and crags of north Wales? May I draw his attention to the circumstances of my constituent, Ric Potter? Like many others, he has had to travel to Scotland, where there is greater access. Will my right hon. Friend help us to enable people such as Ric Potter to find work in outdoor pursuits?

3.1 Full topic model summary - K30

## A topic model with 30 topics, 81607 documents and a 115477 word dictionary.

## Topic 1 Top Words:
##       Highest Prob: bill, amendment, clause, new, legislation, amendments, act 
##       FREX: amendment, clause, amendments, clauses, nos, insert, subsection 
##       Lift: #185, #85, 0.003, 05, 1-competences, 1-impact, 1,924 
##       Score: clause, amendment, amendments, bill, provisions, lords, nos 
## Topic 2 Top Words:
##       Highest Prob: issues, public, information, also, report, review, process 
##       FREX: consultation, review, guidance, recommendations, information, considering, decisions 
##       Lift: 1-who, 1,842, 109648, 1402, 151387, 1981-was, 1a-has 
##       Score: consultation, guidance, information, review, committee, issues, process 
## Topic 3 Top Words:
##       Highest Prob: women, men, pay, equality, rights, women's, discrimination 
##       FREX: women, equality, gender, equalities, bishops, discrimination, female 
##       Lift: gender, #112, #neverthelesshepersisted, 1-breast-feed, 1,087, 1,574, 1.57 
##       Score: women, women's, equality, men, gender, discrimination, girls 
## Topic 4 Top Words:
##       Highest Prob: police, crime, officers, behaviour, policing, home, antisocial 
##       FREX: policing, antisocial, constable, burglary, wardens, crime, constabulary 
##       Lift: 1,113, 1.24, 17,614, acpo's, adz, alcohol-free, alleygator 
##       Score: police, crime, officers, policing, antisocial, behaviour, constable 
## Topic 5 Top Words:
##       Highest Prob: european, uk, countries, eu, union, trade, international 
##       FREX: treaty, enlargement, wto, lisbon, doha, eu, eu's 
##       Lift: #420, 0.26, 0.56, 07, 09, 1-2, 1-of 
##       Score: eu, european, countries, treaty, armed, defence, forces 
## Topic 6 Top Words:
##       Highest Prob: transport, london, rail, bus, road, services, line 
##       FREX: rail, bus, passengers, fares, trains, buses, passenger 
##       Lift: #145, 0.1p, 0.45, 0.86, 1-very, 1,122, 1,658 
##       Score: rail, transport, bus, passengers, fares, trains, congestion 
## Topic 7 Top Words:
##       Highest Prob: people, work, benefit, pension, benefits, support, disabled 
##       FREX: disabled, jobcentre, incapacity, carers, pension, claimants, esa 
##       Lift: dla, #400, 0300, 1-to-1, 1,030, 1,052, 1,366 
##       Score: pension, carers, disabled, pensions, allowance, disability, credit 
## Topic 8 Top Words:
##       Highest Prob: immigration, safety, uk, asylum, enforcement, home, number 
##       FREX: dogs, dog, id, visa, fur, mink, hse 
##       Lift: 44a, a8, acoba, arcs, attachment-free, bareboat, bonfires 
##       Score: immigration, asylum, animals, dogs, fireworks, dog, animal 
## Topic 9 Top Words:
##       Highest Prob: health, research, cancer, treatment, medical, disease, can 
##       FREX: cancer, diseases, vaccine, flu, embryos, infections, diabetes 
##       Lift: 1169, 20-fold, ablation, abnormalities, adpkd, aed, anaesthesia 
##       Score: cancer, patients, disease, smoking, health, diagnosis, screening 
## Topic 10 Top Words:
##       Highest Prob: government, labour, conservative, party, opposition, policy, government's 
##       FREX: conservative, liberal, democrats, conservatives, scottish, democrat, scotland 
##       Lift: #nationalistsconfused, 1-but, 1.135, 10,182, 10.91, 1125, 116385 
##       Score: conservative, scottish, party, labour, government, scotland, liberal 
## Topic 11 Top Words:
##       Highest Prob: care, health, nhs, services, service, hospital, patients 
##       FREX: dentists, ambulance, dentistry, helier, dentist, nurses, hospital 
##       Lift: 2.24, 2005-6, 22,600, 422, 5.45pm, 8.03, 8.41 
##       Score: nhs, patients, care, hospital, health, patient, hospitals 
## Topic 12 Top Words:
##       Highest Prob: member, members, debate, house, mr, committee, said 
##       FREX: member, speaker, mr, debate, spoke, thoughtful, backbench 
##       Lift: e-petitions, @daisydumble, @percyblakeney63, 10,000-signature, 1028, 1080, 11.00 
##       Score: member, mr, committee, members, speaker, debate, house 
## Topic 13 Top Words:
##       Highest Prob: companies, financial, company, market, scheme, money, debt 
##       FREX: payday, annuity, oft, policyholders, penrose, fca, loan 
##       Lift: fca, oft, prepayment, #1.8, #20,000, 0.21, 0.84 
##       Score: companies, consumers, fsa, banks, company, customers, consumer 
## Topic 14 Top Words:
##       Highest Prob: young, people, health, mental, youth, prison, problems 
##       FREX: prisons, probation, cannabis, reoffending, mental, prison, self-harm 
##       Lift: cannabis, hawton, poppers, camhs, inmates, reoffending, #230 
##       Score: young, mental, prison, drugs, alcohol, youth, drug 
## Topic 15 Top Words:
##       Highest Prob: cases, court, legal, law, case, justice, evidence 
##       FREX: judicial, attorney-general, defendant, extradition, tpims, suspects, court 
##       Lift: 110-day, abscond, absconded, acquittals, adduce, anti-viral, babar 
##       Score: court, offence, courts, criminal, justice, prosecution, offences 
## Topic 16 Top Words:
##       Highest Prob: energy, businesses, business, jobs, investment, economy, industry 
##       FREX: carbon, renewable, renewables, solar, low-carbon, energy, feed-in 
##       Lift: fossil, sellafield, viyella, energy-intensive, low-carbon, #12.5, #140,000 
##       Score: energy, businesses, jobs, economy, manufacturing, industry, investment 
## Topic 17 Top Words:
##       Highest Prob: people, want, one, get, know, say, us 
##       FREX: things, think, something, get, want, going, really 
##       Lift: 1,027, 2.85, 30s-will, 6.37, 778, about-part, accept-there 
##       Score: people, get, think, things, going, want, say 
## Topic 18 Top Words:
##       Highest Prob: education, schools, school, children, training, skills, parents 
##       FREX: schools, teachers, pupils, curriculum, sen, academies, ofsted 
##       Lift: ema, #8,000, 1,000-pupil, 1,051, 1,100-i, 1,170, 1,204 
##       Score: schools, school, education, children, teachers, pupils, students 
## Topic 19 Top Words:
##       Highest Prob: constituency, city, people, many, years, work, centre 
##       FREX: fishermen, cod, hull, plymouth, maiden, fishing, fish 
##       Lift: #14.4, #66.6, 0.27, 0.51, 1,084, 1,126, 1.41 
##       Score: plymouth, constituency, hull, city, fishing, fish, arts 
## Topic 20 Top Words:
##       Highest Prob: housing, homes, people, private, london, social, home 
##       FREX: rent, tenants, landlords, rented, homelessness, homeless, rents 
##       Lift: right-to-buy, #19, #21.5, #28.5, 1,000-odd, 1,026, 1,083 
##       Score: housing, homes, rented, rent, tenants, landlords, affordable 
## Topic 21 Top Words:
##       Highest Prob: tax, year, million, government, budget, cuts, cut 
##       FREX: tax, obr, vat, millionaires, 50p, inflation, budget 
##       Lift: 0.38, 1,869, 107,500, 11.2, 13,600, 2,073, 2.33 
##       Score: tax, cuts, budget, poverty, chancellor, unemployment, billion 
## Topic 22 Top Words:
##       Highest Prob: food, post, office, rural, petition, offices, farmers 
##       FREX: petition, farmers, petitioners, meat, cull, labelling, cattle 
##       Lift: #450, 1072, 11,900, 12-point, 934, a690, ablewell 
##       Score: food, farmers, petitioners, petition, post, rural, offices 
## Topic 23 Top Words:
##       Highest Prob: people, international, human, government, war, rights, country 
##       FREX: syria, israel, civilians, palestinian, israeli, gaza, sri 
##       Lift: muslims, #aleppo, #no2lgbthate, 0.002, 1,000-almost, 1,010, 1,019 
##       Score: syria, un, israel, humanitarian, iraq, palestinian, israeli 
## Topic 24 Top Words:
##       Highest Prob: bbc, media, online, internet, sport, access, digital 
##       FREX: bbc, games, olympic, gambling, bbc's, copyright, lap-dancing 
##       Lift: age-restricted, age-verification, aquatics, bacta, bandwidth, bbfc, bduk 
##       Score: bbc, sport, tickets, internet, digital, online, football 
## Topic 25 Top Words:
##       Highest Prob: local, authorities, funding, areas, services, council, community 
##       FREX: local, authorities, funding, councils, grant, authority, formula 
##       Lift: 416,000, 596,000, 82-3, 885, allison's, baccy, bellwin 
##       Score: local, authorities, funding, councils, authority, council, services 
## Topic 26 Top Words:
##       Highest Prob: children, child, families, care, family, parents, violence 
##       FREX: trafficked, csa, same-sex, adopters, child, rape, marriages 
##       Lift: @mandatenow, 1-regardless, 1,000-discriminates, 1,142,600, 1,483, 1,746, 10-month-old 
##       Score: child, children, parents, violence, care, sexual, rape 
## Topic 27 Top Words:
##       Highest Prob: planning, water, development, land, environment, site, sites 
##       FREX: forestry, biodiversity, masts, habitats, gypsy, flood, waterways 
##       Lift: biodiversity, encampments, masts, #tartantories, 0fficial, 1,000-year-old, 1,251 
##       Score: planning, land, flood, marine, sites, water, site 
## Topic 28 Top Words:
##       Highest Prob: secretary, state, house, last, statement, report, said 
##       FREX: secretary, statement, state, confirm, official, answer, vol 
##       Lift: 12.40, ashleys, ayia, burne, cabinet's, cairns's, clutha 
##       Score: secretary, state, statement, answer, confirm, inquiry, leader 
## Topic 29 Top Words:
##       Highest Prob: parliament, wales, vote, commission, political, assembly, people 
##       FREX: electoral, polling, gibraltar, voting, assembly, vote, votes 
##       Lift: @leamingtonsbc, @maggieannehayes, @nhconsortium, #keeptweeting, 1-46, 1-would, 1,294 
##       Score: electoral, vote, elections, wales, assembly, referendum, welsh 
## Topic 30 Top Words:
##       Highest Prob: can, make, ensure, agree, important, take, made 
##       FREX: agree, aware, sure, ensure, taking, lady, welcome 
##       Lift: 1565, 19602, 2,095, 42931, 94254, agencies-an, anguish-filled 
##       Score: agree, aware, thank, ensure, point, lady, can

3.2 Full topic model estimate summary - K30

## 
## Call:
## estimateEffect(formula = 1:30 ~ short_list, stmobj = topic_model_k30, 
##     metadata = lab_corpus_fem_stm$meta, uncertainty = "Global")
## 
## 
## Topic 1:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0449755  0.0006472  69.493 <0.0000000000000002 ***
## short_listTRUE -0.0068779  0.0008151  -8.439 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 2:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0757511  0.0006095  124.28 <0.0000000000000002 ***
## short_listTRUE -0.0215037  0.0007218  -29.79 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 3:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0230304  0.0006035  38.161 <0.0000000000000002 ***
## short_listTRUE -0.0007445  0.0006951  -1.071               0.284    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 4:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0289390  0.0006449  44.870 <0.0000000000000002 ***
## short_listTRUE -0.0074465  0.0007507  -9.919 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 5:
## 
## Coefficients:
##                  Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)     0.0368433  0.0006683  55.128 < 0.0000000000000002 ***
## short_listTRUE -0.0050970  0.0007776  -6.555      0.0000000000559 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 6:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0217966  0.0005682   38.36 < 0.0000000000000002 ***
## short_listTRUE 0.0054412  0.0007568    7.19    0.000000000000653 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 7:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0298430  0.0006534   45.68 <0.0000000000000002 ***
## short_listTRUE 0.0131664  0.0007960   16.54 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 8:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0186040  0.0004866  38.233 <0.0000000000000002 ***
## short_listTRUE 0.0004542  0.0006331   0.717               0.473    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 9:
## 
## Coefficients:
##                  Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)     0.0249398  0.0005900  42.274 < 0.0000000000000002 ***
## short_listTRUE -0.0050920  0.0007184  -7.087     0.00000000000138 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 10:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0378826  0.0004769  79.442 < 0.0000000000000002 ***
## short_listTRUE 0.0020076  0.0005988   3.353             0.000801 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 11:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0407964  0.0006946  58.736 <0.0000000000000002 ***
## short_listTRUE -0.0083296  0.0008782  -9.485 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 12:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0389920  0.0005983   65.17 <0.0000000000000002 ***
## short_listTRUE 0.0082206  0.0007271   11.31 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 13:
## 
## Coefficients:
##                  Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)     0.0302234  0.0006155  49.102 < 0.0000000000000002 ***
## short_listTRUE -0.0028531  0.0007772  -3.671             0.000241 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 14:
## 
## Coefficients:
##                  Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)     0.0239267  0.0005272   45.38 < 0.0000000000000002 ***
## short_listTRUE -0.0032073  0.0006326   -5.07          0.000000398 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 15:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0409498  0.0006912   59.24 <0.0000000000000002 ***
## short_listTRUE -0.0167429  0.0008410  -19.91 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 16:
## 
## Coefficients:
##                  Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)     0.0384203  0.0006693  57.403 < 0.0000000000000002 ***
## short_listTRUE -0.0046108  0.0008739  -5.276          0.000000132 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 17:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0788541  0.0005734 137.511 < 0.0000000000000002 ***
## short_listTRUE 0.0019922  0.0007215   2.761              0.00576 ** 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 18:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0298378  0.0006936  43.018 < 0.0000000000000002 ***
## short_listTRUE 0.0038174  0.0008514   4.483           0.00000735 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 19:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0196109  0.0005058   38.77 <0.0000000000000002 ***
## short_listTRUE 0.0092466  0.0006647   13.91 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 20:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0204377  0.0005469  37.372 < 0.0000000000000002 ***
## short_listTRUE 0.0038546  0.0007434   5.185          0.000000216 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 21:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0460818  0.0008017   57.48 <0.0000000000000002 ***
## short_listTRUE 0.0143004  0.0010069   14.20 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 22:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0139579  0.0004672  29.879 <0.0000000000000002 ***
## short_listTRUE 0.0055290  0.0005755   9.608 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 23:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0261672  0.0006795  38.507 <0.0000000000000002 ***
## short_listTRUE 0.0007523  0.0008413   0.894               0.371    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 24:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0124090  0.0003942  31.477 <0.0000000000000002 ***
## short_listTRUE 0.0049032  0.0004912   9.983 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 25:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0426122  0.0006095   69.91 <0.0000000000000002 ***
## short_listTRUE -0.0085951  0.0007406  -11.61 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 26:
## 
## Coefficients:
##                   Estimate  Std. Error t value            Pr(>|t|)    
## (Intercept)     0.02500845  0.00056664  44.134 <0.0000000000000002 ***
## short_listTRUE -0.00001695  0.00073195  -0.023               0.982    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 27:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0149391  0.0004787  31.208 <0.0000000000000002 ***
## short_listTRUE 0.0003306  0.0005963   0.554               0.579    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 28:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0427050  0.0005816   73.42 <0.0000000000000002 ***
## short_listTRUE 0.0145487  0.0007200   20.21 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 29:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0187999  0.0005248  35.823 <0.0000000000000002 ***
## short_listTRUE 0.0063006  0.0006838   9.214 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 30:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0526695  0.0003205 164.348 <0.0000000000000002 ***
## short_listTRUE -0.0037490  0.0003892  -9.634 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

3.3 AWS References to Constituents in Context

A random selection of 2% of all references to “my constituency”, “my constituent” and “my constituents”, by AWS MPs, in context.

3.3.1 Short lists vs Non-Short lists - K69

The first implementation used an algorithm developed by Lee & Mimno (2014), implemented in the stm package (Roberts et al., 2018), to estimate the number of topics across all speeches made by female Labour MPs, using the “spectral” method developed by Arora et al. (2013), implemented by Roberts et al. (2018). The resulting topic model has 69 topics, across 81,607 documents and a dictionary of 115,477 words. However, the topic quality with K = 69 is poor, and several topics have poor semantic coherence (see ).

There are several clusters of topics in . For instance, we can see the closeness of Topic 15 (unemployment) and Topic 43 (housing), as both are social issues include discussions of budgets and costs, while Topics 23 (bill amendments) and 16 (education) are very far apart.

Fruchterman-Reingold plot of K69 Network

Coherence of K69 Topic Models

Count and Distribution of Topics – K69

Topic Number	AWS Speeches	Percent of AWS Speeches	Non-AWS Speeches	Percent of non-AWS Speeches	Male MP Speeches	Percent of Male MP Speeches
Topic 1	1,272	2.37%	353	1.27%	3,434	2.03%
Topic 2	334	0.62%	127	0.46%	1,091	0.64%
Topic 3	241	0.45%	71	0.25%	427	0.25%
Topic 4	550	1.02%	133	0.48%	835	0.49%
Topic 5	826	1.54%	206	0.74%	2,452	1.45%
Topic 6	978	1.82%	915	3.28%	4,060	2.4%
Topic 7	648	1.21%	236	0.85%	1,770	1.05%
Topic 8	70	0.13%	25	0.09%	125	0.07%
Topic 9	265	0.49%	309	1.11%	862	0.51%
Topic 10	1,024	1.91%	513	1.84%	1,065	0.63%
Topic 11	940	1.75%	580	2.08%	3,793	2.24%
Topic 12	313	0.58%	319	1.14%	1,309	0.77%
Topic 13	325	0.61%	146	0.52%	1,181	0.7%
Topic 14	1,596	2.97%	461	1.65%	2,885	1.7%
Topic 15	1,386	2.58%	642	2.3%	4,686	2.77%
Topic 16	1,407	2.62%	525	1.88%	3,651	2.16%
Topic 17	3,690	6.87%	1,459	5.23%	19,359	11.43%
Topic 18	1,026	1.91%	847	3.04%	4,760	2.81%
Topic 19	640	1.19%	423	1.52%	2,130	1.26%
Topic 20	872	1.62%	216	0.77%	2,262	1.34%
Topic 21	658	1.23%	363	1.3%	914	0.54%
Topic 22	818	1.52%	439	1.57%	1,965	1.16%
Topic 23	795	1.48%	518	1.86%	3,553	2.1%
Topic 24	385	0.72%	199	0.71%	1,079	0.64%
Topic 25	240	0.45%	74	0.27%	422	0.25%
Topic 26	788	1.47%	200	0.72%	1,738	1.03%
Topic 27	266	0.5%	120	0.43%	1,010	0.6%
Topic 28	847	1.58%	350	1.25%	3,135	1.85%
Topic 29	1,110	2.07%	327	1.17%	944	0.56%
Topic 30	1,132	2.11%	462	1.66%	6,444	3.81%
Topic 31	996	1.85%	975	3.49%	6,077	3.59%
Topic 32	76	0.14%	64	0.23%	335	0.2%
Topic 33	1,238	2.31%	985	3.53%	6,613	3.9%
Topic 34	1,124	2.09%	521	1.87%	3,335	1.97%
Topic 35	650	1.21%	657	2.35%	2,294	1.35%
Topic 36	601	1.12%	154	0.55%	548	0.32%
Topic 37	455	0.85%	194	0.7%	1,554	0.92%
Topic 38	1,246	2.32%	991	3.55%	2,849	1.68%
Topic 39	1,917	3.57%	936	3.35%	7,664	4.53%
Topic 40	848	1.58%	290	1.04%	2,419	1.43%
Topic 41	63	0.12%	40	0.14%	204	0.12%
Topic 42	853	1.59%	590	2.11%	2,016	1.19%
Topic 43	1,344	2.5%	604	2.16%	2,266	1.34%
Topic 44	814	1.52%	288	1.03%	3,005	1.77%
Topic 45	602	1.12%	474	1.7%	1,086	0.64%
Topic 46	709	1.32%	150	0.54%	1,646	0.97%
Topic 47	664	1.24%	245	0.88%	2,992	1.77%
Topic 48	940	1.75%	901	3.23%	3,045	1.8%
Topic 49	835	1.55%	563	2.02%	2,537	1.5%
Topic 50	1,328	2.47%	1,219	4.37%	3,421	2.02%
Topic 51	1,076	2%	323	1.16%	2,453	1.45%
Topic 52	196	0.36%	85	0.3%	758	0.45%
Topic 53	590	1.1%	293	1.05%	746	0.44%
Topic 54	1,057	1.97%	824	2.95%	5,570	3.29%
Topic 55	302	0.56%	157	0.56%	868	0.51%
Topic 56	535	1%	398	1.43%	847	0.5%
Topic 57	656	1.22%	314	1.13%	1,990	1.18%
Topic 58	468	0.87%	182	0.65%	1,125	0.66%
Topic 59	426	0.79%	183	0.66%	700	0.41%
Topic 60	562	1.05%	297	1.06%	1,389	0.82%
Topic 61	86	0.16%	28	0.1%	174	0.1%
Topic 62	550	1.02%	343	1.23%	746	0.44%
Topic 63	690	1.28%	252	0.9%	1,726	1.02%
Topic 64	594	1.11%	244	0.87%	2,247	1.33%
Topic 65	662	1.23%	457	1.64%	907	0.54%
Topic 66	1,493	2.78%	527	1.89%	4,073	2.41%
Topic 67	737	1.37%	451	1.62%	3,237	1.91%
Topic 68	279	0.52%	145	0.52%	547	0.32%
Topic 69	1	0%	NA	NA%	NA	NA%

K69 Pyramid Chart

K69 Bar Chart

3.3.1.1 Word Occurences

The table below shows the ten most common words in each topic, and the ten words with the highest FREX score, a measure that uses a harmonic mean of word exclusivity and topic coherence (Airoldi & Bischof, 2016).

Words in topic - K69

Topic Number	Top Ten Words	Top Ten FREX
Topic 1	secretary, state, tell, ministers, given, today, department, can, confirm, said	secretary, state, confirm, tell, ministers, state’s, minister’s, explain, please, discussions
Topic 2	safety, register, registration, indicated, registered, electoral, risk, risks, number, individual	registration, indicated, hse, canvass, register, gurkhas, safety, dissent, hare, trustee
Topic 3	make, sure, statement, progress, difference, northern, ireland, towards, representations, responsibilities	statement, make, sure, progress, ireland, representations, difference, northern, milton, departmental
Topic 4	debt, water, credit, charges, pay, loan, loans, people, financial, cost	payday, loan, lenders, debts, loans, debt, charges, water, high-cost, creditors
Topic 5	house, committee, parliament, leader, select, motion, parliamentary, debate, scrutiny, business	select, leader, house, motion, committee, backbench, scrutiny, committees, benchers, parliamentary
Topic 6	new, development, work, need, investment, strategy, must, programme, working, also	development, strategy, develop, project, regional, projects, partnership, together, developed, build
Topic 7	road, petition, residents, car, vehicles, petitioners, dogs, roads, site, house	petitioners, lap-dancing, petition, dogs, dog, pedestrians, cycling, declares, drivers, accidents
Topic 8	important, agree, welcome, country, making, particularly, thank, part, makes, good	agree, welcome, important, absolutely, makes, making, friend’s, thank, particularly, giving
Topic 9	companies, market, company, competition, energy, consumers, prices, price, consumer, customers	competition, companies, market, wholesale, suppliers, company, regulator, ofgem, supplier, consumers
Topic 10	women, men, equality, women’s, discrimination, rights, gender, equal, woman, marriage	gender, bishops, transgender, women’s, women, abortion, same-sex, marriage, equality, gay
Topic 11	energy, climate, fuel, change, green, carbon, emissions, gas, environmental, industry	renewables, solar, insulation, feed-in, biofuels, greenhouse, dioxide, kyoto, carbon, climate
Topic 12	office, post, offices, royal, service, closure, mail, services, network, christmas	offices, mail, sub-post, post, sub-postmasters, closures, consignia, swindon, closure, office
Topic 13	mr, north, south, east, west, spoke, friends, birmingham, talked, central	ealing, spoke, dorset, lothian, ayrshire, glasgow, chris, southwark, pontefract, birmingham
Topic 14	pension, scheme, benefit, pensions, benefits, pensioners, system, credit, allowance, income	pension, esa, pensions, claimants, retirement, pip, pensioners, incapacity, dwp, means-testing
Topic 15	economy, jobs, economic, growth, unemployment, country, investment, chancellor, budget, crisis	unemployment, recession, growth, economy, obr, deficit, inflation, economic, forecast, borrowing
Topic 16	schools, school, education, children, teachers, parents, pupils, educational, special, primary	academies, pupil, grammar, schools, pupils, teachers, ofsted, school, teacher, sen
Topic 17	want, say, one, think, know, need, us, get, go, see	think, say, things, want, something, saying, going, lot, really, go
Topic 18	review, report, commission, independent, process, recommendations, inquiry, also, system, standards	recommendations, inquiry, panel, audit, independent, recommendation, reviews, fsa, complaints, review
Topic 19	business, businesses, small, financial, bank, banks, insurance, rates, industry, enterprise	smes, medium-sized, businesses, bank, enterprises, enterprise, banking, rbs, business, rock
Topic 20	wales, industry, welsh, north-east, england, assembly, constituency, jobs, manufacturing, uk	welsh, wales, steel, cardiff, north-east, assembly, visteon, newcastle, manufacturing, tyneside
Topic 21	care, services, social, mental, need, health, home, provision, service, older	mental, care, social, elderly, older, advocacy, services, residential, palliative, discharges
Topic 22	pay, work, workers, employment, working, wage, minimum, employers, paid, national	wage, workers, zero-hours, employees, paternity, employer, minimum, employers, employment, workplace
Topic 23	amendment, clause, amendments, new, 1, lords, section, 2, act, clauses	amendment, nos, insert, subsection, clause, amendments, clauses, section, lords, schedule
Topic 24	report, last, since, said, received, published, year, following, official, end	march, vol, official, january, july, november, published, december, june, october
Topic 25	made, clear, impact, decision, changes, recent, assessment, decisions, effect, proposed	made, decision, assessment, clear, decisions, impact, implications, recent, changes, effect
Topic 26	funding, cuts, fund, cut, budget, grant, spending, bbc, review, flood	flood, funding, bbc, formula, grant, flooding, floods, cumbria, lottery, grants
Topic 27	money, spent, extra, spend, liberal, cost, spending, value, opposition, tory	money, spent, liberal, spend, democrats, tories, tory, lib, democrat, conservatives
Topic 28	constituency, great, community, proud, many, sport, one, also, world, new	maiden, arts, football, museum, museums, sport, olympic, games, sports, heritage
Topic 29	families, child, poverty, children, parents, work, credit, working, family, living	lone, poverty, childcare, families, low-income, child, nursery, four-year-olds, nurseries, joseph
Topic 30	party, conservative, vote, parliament, political, election, labour, parties, scottish, elected	party, vote, voting, conservative, party’s, voters, election, voted, votes, politics
Topic 31	point, can, may, issue, take, however, whether, matter, understand, consider	matter, point, understand, consider, certainly, accept, possible, issue, course, happy
Topic 32	member, said, lady, mentioned, raised, comments, speech, referred, points, remarks	member, lady, comments, remarks, bromley, interesting, chislehurst, pointed, front-bench, mentioned
Topic 33	european, uk, eu, countries, united, union, europe, states, british, trade	accession, enlargement, wto, lisbon, treaty, eu, doha, european, negotiations, brexit
Topic 34	education, skills, young, training, students, university, college, higher, science, apprenticeships	ema, fe, students, apprenticeship, universities, qualifications, apprenticeships, graduates, vocational, courses
Topic 35	local, authorities, authority, planning, community, communities, councils, area, guidance, system	authorities, local, authority, planning, councils, councillors, locally, guidance, localism, communities
Topic 36	disabled, carers, disability, support, disabilities, needs, caring, autism, learning, can	carers, autism, autistic, disabled, disabilities, disability, dementia, carer, caring, deaf
Topic 37	environment, marine, fishing, sea, industry, natural, fish, countryside, rural, fisheries	fishermen, cod, forestry, biodiversity, habitats, mmo, fishing, fish, cfp, fisheries
Topic 38	justice, court, violence, victims, cases, criminal, domestic, courts, prison, offence	attorney-general, defendants, defendant, prison, prosecutors, solicitor-general, stalking, prosecutor, prisons, prosecution
Topic 39	international, foreign, rights, human, peace, un, conflict, world, aid, war	israel, palestinian, israeli, gaza, sri, zimbabwe, iran, yemen, hamas, palestinians
Topic 40	day, family, never, told, families, life, happened, constituent, man, went	man, died, son, story, stories, hillsborough, tragedy, daughter, husband, angry
Topic 41	proposals, future, forward, consultation, plans, meet, paper, current, discuss, bring	proposals, consultation, paper, plans, forward, discuss, white, proposal, meet, implement
Topic 42	behaviour, crime, antisocial, alcohol, young, drugs, drug, problem, use, tackle	antisocial, asbos, alcohol, alcohol-related, binge, psychoactive, drinking, fireworks, behaviour, graffiti
Topic 43	housing, homes, social, affordable, private, home, accommodation, rent, need, properties	housing, tenants, rented, tenancies, homelessness, leasehold, landlords, rents, properties, leaseholders
Topic 44	question, order, mr, put, asked, answer, questions, ask, speaker, time	question, answer, questions, speaker, asked, deputy, answers, order, apologise, read
Topic 45	research, cancer, treatment, medical, condition, screening, disease, can, patients, use	embryos, prostate, cervical, hepatitis, cloning, transplant, embryo, fertilisation, embryonic, endometriosis
Topic 46	online, internet, farmers, animals, digital, animal, broadband, sites, tickets, technology	cull, badgers, badger, fur, bovine, mink, culling, circuses, touts, snares
Topic 47	defence, forces, armed, plymouth, personnel, service, military, army, nuclear, royal	mod, naval, hms, submarines, dockyard, veterans, armed, plymouth, covenant, personnel
Topic 48	information, home, security, data, immigration, control, orders, system, terrorism, appeal	extradition, tpims, sia, warrant, detention, checks, tpim, terrorism, intercept, identity
Topic 49	police, officers, crime, policing, home, force, service, forces, officer, chief	constable, constables, officers, policing, police, soca, ipcc, constabulary, pcsos, hmic
Topic 50	nhs, hospital, patients, health, services, hospitals, care, service, trust, trusts	dentists, dentistry, pharmacies, pct, nhs, hospitals, hospital, dental, trusts, patients
Topic 51	tax, budget, cut, chancellor, cuts, rate, income, vat, benefit, hit	50p, vat, millionaires, hit, tax, allowances, credits, richest, chancellor, ifs
Topic 52	years, now, two, time, first, three, past, one, months, ago	years, three, months, ago, two, past, weeks, five, four, now
Topic 53	staff, doctors, emergency, medical, service, training, nurses, royal, junior, ambulance	ambulance, junior, staffing, doctors, halifax, posts, nurses, fss, staff, cpr
Topic 54	bill, legislation, act, law, rights, provisions, powers, regulations, place, believe	bill, legislation, bill’s, provisions, passage, regulations, legislative, draft, statute, definition
Topic 55	public, sector, private, organisations, service, voluntary, services, society, community, organisation	public, voluntary, organisations, sector, private, co-operative, volunteering, volunteers, volunteer, co-operatives
Topic 56	health, national, inequalities, programme, suicide, disease, department, prevention, among, risk	flu, hiv, pandemic, inequalities, infections, suicide, mortality, infection, mrsa, vaccine
Topic 57	council, london, areas, city, area, constituency, centre, rural, county, liverpool	county, mayor, borough, cities, liverpool, city, regeneration, council’s, london, towns
Topic 58	advice, legal, cases, civil, hull, aid, case, compensation, claims, service	hull, tribunal, legal, compensation, solicitors, advice, concentrix, servants, lawyers, tribunals
Topic 59	people, work, many, young, get, people’s, can, help, lives, job	people, people’s, get, getting, work, young, jobcentre, lives, youth, find
Topic 60	tax, revenue, relief, duty, uk, avoidance, hmrc, charities, companies, taxation	evasion, hmrc, gaar, avoidance, inland, stamp, revenue, relief, gift, dependencies
Topic 61	government, government’s, policy, labour, previous, scotland, scottish, commitment, policies, coalition	government, previous, policy, government’s, scotland, coalition, scottish, labour, disappointing, administrations
Topic 62	trafficking, home, uk, asylum, refugees, immigration, country, human, migration, britain	trafficking, slavery, trafficked, sierra, leone, slave, dubs, fgm, yarl’s, wilberforce
Topic 63	food, products, industry, smoking, advertising, tobacco, ban, product, standards, shops	gambling, betting, sunbed, tobacco, cocoa, meat, supermarkets, labelling, retailers, packaging
Topic 64	members, debate, many, issues, also, today, heard, opportunity, hope, issue	members, debate, heard, speak, sides, issues, hear, opportunity, listened, pleased
Topic 65	children, child, parents, young, children’s, family, contact, vulnerable, adoption, abuse	csa, adopters, adoption, child’s, cafcass, looked-after, children’s, children, safeguarding, barred
Topic 66	transport, rail, bus, services, line, travel, train, network, passengers, london	rail, passengers, passenger, heathrow, hs2, freight, high-speed, crossrail, airlines, runway
Topic 67	year, million, number, increase, figures, increased, billion, 1, average, cost	million, figures, figure, increased, increase, compared, year, total, fallen, estimates
Topic 68	support, ensure, can, help, aware, taking, take, provide, action, continue	aware, ensure, support, taking, steps, continue, help, action, assure, encourage
Topic 69	deal, recently, new, can, lack, great, concern, done, move, given	deal, recently, lack, elsewhere, concern, great, improved, offered, done, new

3.4 Full topic model summary - K69

## A topic model with 69 topics, 81607 documents and a 115477 word dictionary.

## Topic 1 Top Words:
##       Highest Prob: secretary, state, tell, ministers, given, today, department 
##       FREX: secretary, state, confirm, tell, ministers, state's, minister's 
##       Lift: dhar, lowell, qatada's, #nationalistsconfused, 1135, 2.5bn, 36,500 
##       Score: secretary, state, confirm, state's, tell, ministers, department 
## Topic 2 Top Words:
##       Highest Prob: safety, register, registration, indicated, registered, electoral, risk 
##       FREX: registration, indicated, hse, canvass, register, gurkhas, safety 
##       Lift: aps, hse, 10-litre, 13a, 14,940, 1760, 1867 
##       Score: safety, registration, register, electoral, indicated, registered, hse 
## Topic 3 Top Words:
##       Highest Prob: make, sure, statement, progress, difference, northern, ireland 
##       FREX: statement, make, sure, progress, ireland, representations, difference 
##       Lift: 101269, 101548, 102938, 103414, 106583, 107305, 109413 
##       Score: make, statement, progress, sure, ireland, northern, milton 
## Topic 4 Top Words:
##       Highest Prob: debt, water, credit, charges, pay, loan, loans 
##       FREX: payday, loan, lenders, debts, loans, debt, charges 
##       Lift: 1,021, 1,025, 1,106, 1,189, 1,273, 1,385, 1,413 
##       Score: debt, water, payday, loan, loans, lenders, credit 
## Topic 5 Top Words:
##       Highest Prob: house, committee, parliament, leader, select, motion, parliamentary 
##       FREX: select, leader, house, motion, committee, backbench, scrutiny 
##       Lift: e-petitions, praying-against, sherlock, wednesdays, sittings, thursdays, 10,000-signature 
##       Score: committee, house, leader, select, scrutiny, parliament, motion 
## Topic 6 Top Words:
##       Highest Prob: new, development, work, need, investment, strategy, must 
##       FREX: development, strategy, develop, project, regional, projects, partnership 
##       Lift: #1,150, 1.245, 1.875, 128406, 131,000, 18-the, 2002-around 
##       Score: development, regional, investment, strategy, infrastructure, projects, work 
## Topic 7 Top Words:
##       Highest Prob: road, petition, residents, car, vehicles, petitioners, dogs 
##       FREX: petitioners, lap-dancing, petition, dogs, dog, pedestrians, cycling 
##       Lift: 0.037, 0.044, 0fficial, 1,042, 1,072, 1,108, 1,122 
##       Score: petitioners, petition, dogs, road, residents, dog, declares 
## Topic 8 Top Words:
##       Highest Prob: important, agree, welcome, country, making, particularly, thank 
##       FREX: agree, welcome, important, absolutely, makes, making, friend's 
##       Lift: adequacies, and-importantly-much, ayse, ballantine, bobtail-and, bostrom, bucketfuls 
##       Score: agree, important, thank, welcome, friend's, absolutely, country 
## Topic 9 Top Words:
##       Highest Prob: companies, market, company, competition, energy, consumers, prices 
##       FREX: competition, companies, market, wholesale, suppliers, company, regulator 
##       Lift: 1,105, 1,345, ashington, boakye, nord, over-charging, price-fixing 
##       Score: companies, consumers, energy, market, company, prices, competition 
## Topic 10 Top Words:
##       Highest Prob: women, men, equality, women's, discrimination, rights, gender 
##       FREX: gender, bishops, transgender, women's, women, abortion, same-sex 
##       Lift: balmforth, bpas, celebrants, cohabitants, jessy, msafiri, natal 
##       Score: women, women's, equality, men, gender, discrimination, marriage 
## Topic 11 Top Words:
##       Highest Prob: energy, climate, fuel, change, green, carbon, emissions 
##       FREX: renewables, solar, insulation, feed-in, biofuels, greenhouse, dioxide 
##       Lift: fossil, #2,500, #solar, 1-are, 1,129, 1,214, 1,343 
##       Score: energy, fuel, carbon, emissions, climate, renewable, renewables 
## Topic 12 Top Words:
##       Highest Prob: office, post, offices, royal, service, closure, mail 
##       FREX: offices, mail, sub-post, post, sub-postmasters, closures, consignia 
##       Lift: #1.8, #210, #450, 1,001, 1,352, 1,639, 1,827 
##       Score: post, offices, office, mail, closure, postal, sub-post 
## Topic 13 Top Words:
##       Highest Prob: mr, north, south, east, west, spoke, friends 
##       FREX: ealing, spoke, dorset, lothian, ayrshire, glasgow, chris 
##       Lift: argos's, blackford, cairns's, clemency, marxist, no2id, 0.66 
##       Score: mr, east, north, south, west, spoke, birmingham 
## Topic 14 Top Words:
##       Highest Prob: pension, scheme, benefit, pensions, benefits, pensioners, system 
##       FREX: pension, esa, pensions, claimants, retirement, pip, pensioners 
##       Lift: means-testing, #20,000, #400, 0º, 1,052, 1,366, 1,482 
##       Score: pension, pensions, pensioners, allowance, scheme, retirement, credit 
## Topic 15 Top Words:
##       Highest Prob: economy, jobs, economic, growth, unemployment, country, investment 
##       FREX: unemployment, recession, growth, economy, obr, deficit, inflation 
##       Lift: 0.76, 0.83, 1,196, 1,319, 1.04, 1.32, 10-about 
##       Score: economy, jobs, unemployment, growth, economic, recession, chancellor 
## Topic 16 Top Words:
##       Highest Prob: schools, school, education, children, teachers, parents, pupils 
##       FREX: academies, pupil, grammar, schools, pupils, teachers, ofsted 
##       Lift: sen2, 11-plus, leas, pupil, 000-to, 1-regardless, 1,000-pupil 
##       Score: schools, school, teachers, pupils, children, education, parents 
## Topic 17 Top Words:
##       Highest Prob: want, say, one, think, know, need, us 
##       FREX: think, say, things, want, something, saying, going 
##       Lift: about-part, arguing-i, beneficial-we, career-many, cause-the, clam, compatriot 
##       Score: think, want, get, say, things, going, us 
## Topic 18 Top Words:
##       Highest Prob: review, report, commission, independent, process, recommendations, inquiry 
##       FREX: recommendations, inquiry, panel, audit, independent, recommendation, reviews 
##       Lift: bourn, cag's, clarke's, clowes, dg, emag, equitable's 
##       Score: fsa, inquiry, review, commission, recommendations, report, independent 
## Topic 19 Top Words:
##       Highest Prob: business, businesses, small, financial, bank, banks, insurance 
##       FREX: smes, medium-sized, businesses, bank, enterprises, enterprise, banking 
##       Lift: 0.21, 0.84, 1,034, 1,130, 10-fold, 1130, 12.19 
##       Score: businesses, business, bank, banks, banking, insurance, small 
## Topic 20 Top Words:
##       Highest Prob: wales, industry, welsh, north-east, england, assembly, constituency 
##       FREX: welsh, wales, steel, cardiff, north-east, assembly, visteon 
##       Lift: a55, angharad, bethesda, co-investment, dewhirst, dogger, gorge 
##       Score: wales, welsh, assembly, manufacturing, steel, north-east, yorkshire 
## Topic 21 Top Words:
##       Highest Prob: care, services, social, mental, need, health, home 
##       FREX: mental, care, social, elderly, older, advocacy, services 
##       Lift: #900,000, 1,051, 1,312, 10,758, 104962, 1089, 13,198 
##       Score: care, mental, services, social, health, older, homes 
## Topic 22 Top Words:
##       Highest Prob: pay, work, workers, employment, working, wage, minimum 
##       FREX: wage, workers, zero-hours, employees, paternity, employer, minimum 
##       Lift: 6.70, 8.20, 85p, awb, e-balloting, hannett, increments 
##       Score: wage, workers, employers, employment, pay, employees, minimum 
## Topic 23 Top Words:
##       Highest Prob: amendment, clause, amendments, new, 1, lords, section 
##       FREX: amendment, nos, insert, subsection, clause, amendments, clauses 
##       Lift: 153a, 22a, 287, 50b, 51b, counter-notice, insured's 
##       Score: clause, amendment, amendments, lords, nos, insert, subsection 
## Topic 24 Top Words:
##       Highest Prob: report, last, since, said, received, published, year 
##       FREX: march, vol, official, january, july, november, published 
##       Lift: 1-2ws, 1,033, 1,099, 1,124,818, 1,337, 1,368,186, 1,595 
##       Score: report, official, vol, published, march, april, november 
## Topic 25 Top Words:
##       Highest Prob: made, clear, impact, decision, changes, recent, assessment 
##       FREX: made, decision, assessment, clear, decisions, impact, implications 
##       Lift: 104963, 107312, 116,400, 125214, 125828, 125830, 126370 
##       Score: made, assessment, impact, changes, decision, decisions, clear 
## Topic 26 Top Words:
##       Highest Prob: funding, cuts, fund, cut, budget, grant, spending 
##       FREX: flood, funding, bbc, formula, grant, flooding, floods 
##       Lift: #10.89, #12, #3.3, #bbcdiversity, 1,027, 1,536-will, 1,546 
##       Score: funding, cuts, flood, bbc, budget, spending, flooding 
## Topic 27 Top Words:
##       Highest Prob: money, spent, extra, spend, liberal, cost, spending 
##       FREX: money, spent, liberal, spend, democrats, tories, tory 
##       Lift: 1-but, 10,309.63, 1228, 158.8, 1763, 18-that, 1979-80 
##       Score: money, liberal, tory, democrats, conservatives, tories, spending 
## Topic 28 Top Words:
##       Highest Prob: constituency, great, community, proud, many, sport, one 
##       FREX: maiden, arts, football, museum, museums, sport, olympic 
##       Lift: 0.27, 0.51, 1,084, 1,126, 1,468, 1,580-plus, 1,983 
##       Score: arts, sport, museum, maiden, heritage, football, constituency 
## Topic 29 Top Words:
##       Highest Prob: families, child, poverty, children, parents, work, credit 
##       FREX: lone, poverty, childcare, families, low-income, child, nursery 
##       Lift: 1,000-discriminates, 1,000-not, 1,080, 1,142,600, 1,170, 1,390, 1,664 
##       Score: poverty, child, families, children, parents, credit, lone 
## Topic 30 Top Words:
##       Highest Prob: party, conservative, vote, parliament, political, election, labour 
##       FREX: party, vote, voting, conservative, party's, voters, election 
##       Lift: alphabetical, gentry, olga, one-party, randomisation, 1,166, 1,294 
##       Score: party, conservative, vote, scottish, election, elections, political 
## Topic 31 Top Words:
##       Highest Prob: point, can, may, issue, take, however, whether 
##       FREX: matter, point, understand, consider, certainly, accept, possible 
##       Lift: 450,000-in, advised-by, backslid, bill-albeit, bizarre-but, can-enable, cases-roughly 
##       Score: point, matter, issue, gentleman's, consider, shall, whether 
## Topic 32 Top Words:
##       Highest Prob: member, said, lady, mentioned, raised, comments, speech 
##       FREX: member, lady, comments, remarks, bromley, interesting, chislehurst 
##       Lift: 12.20, 130b, 1991-forcing, 2,784, 54,000-worth, achieved-is, arguments-and 
##       Score: member, lady, comments, said, speech, raised, points 
## Topic 33 Top Words:
##       Highest Prob: european, uk, eu, countries, united, union, europe 
##       FREX: accession, enlargement, wto, lisbon, treaty, eu, doha 
##       Lift: 13652, 13653, 13654, 1707, balkan, barnier, blackmailing 
##       Score: eu, european, countries, union, treaty, europe, trade 
## Topic 34 Top Words:
##       Highest Prob: education, skills, young, training, students, university, college 
##       FREX: ema, fe, students, apprenticeship, universities, qualifications, apprenticeships 
##       Lift: ema, #ne, 1,188, 1,308, 1,555-what, 1,740, 1,803 
##       Score: students, education, young, skills, apprenticeships, training, universities 
## Topic 35 Top Words:
##       Highest Prob: local, authorities, authority, planning, community, communities, councils 
##       FREX: authorities, local, authority, planning, councils, councillors, locally 
##       Lift: achcew, central-local, laa, lsp, maas, observances, place-shaping 
##       Score: local, authorities, authority, councils, planning, communities, community 
## Topic 36 Top Words:
##       Highest Prob: disabled, carers, disability, support, disabilities, needs, caring 
##       FREX: carers, autism, autistic, disabled, disabilities, disability, dementia 
##       Lift: autism, rnib, #185, #85, #hellomynameis, 1,400-one, 10-person 
##       Score: carers, disabled, disability, autism, disabilities, caring, dementia 
## Topic 37 Top Words:
##       Highest Prob: environment, marine, fishing, sea, industry, natural, fish 
##       FREX: fishermen, cod, forestry, biodiversity, habitats, mmo, fishing 
##       Lift: aquaculture, arable, bee-friendly, biodiversity, birdlife, bycatch, caterpillar 
##       Score: marine, fishing, fishermen, fish, fisheries, wildlife, conservation 
## Topic 38 Top Words:
##       Highest Prob: justice, court, violence, victims, cases, criminal, domestic 
##       FREX: attorney-general, defendants, defendant, prison, prosecutors, solicitor-general, stalking 
##       Lift: #9, 0.08, 0.48, 1,046, 1,237, 10,544, 10.15 
##       Score: violence, prison, court, offence, criminal, rape, victims 
## Topic 39 Top Words:
##       Highest Prob: international, foreign, rights, human, peace, un, conflict 
##       FREX: israel, palestinian, israeli, gaza, sri, zimbabwe, iran 
##       Lift: lankan, saddam, #aleppo, 1,010, 1,476, 1,591, 1224 
##       Score: un, israel, syria, humanitarian, palestinian, israeli, iraq 
## Topic 40 Top Words:
##       Highest Prob: day, family, never, told, families, life, happened 
##       FREX: man, died, son, story, stories, hillsborough, tragedy 
##       Lift: 10,000-seat, 12-inch, 1234, 1519-20, 1635, 1710, 174,995 
##       Score: families, holocaust, family, constituent, man, died, mother 
## Topic 41 Top Words:
##       Highest Prob: proposals, future, forward, consultation, plans, meet, paper 
##       FREX: proposals, consultation, paper, plans, forward, discuss, white 
##       Lift: 10.42, 107910, 109648, 114061, 119621, 141605, 141607 
##       Score: proposals, consultation, plans, future, forward, paper, white 
## Topic 42 Top Words:
##       Highest Prob: behaviour, crime, antisocial, alcohol, young, drugs, drug 
##       FREX: antisocial, asbos, alcohol, alcohol-related, binge, psychoactive, drinking 
##       Lift: acquisitive, addaction, auto, bailes, crawlers, ghb, gilpin 
##       Score: antisocial, crime, behaviour, alcohol, drug, drugs, cannabis 
## Topic 43 Top Words:
##       Highest Prob: housing, homes, social, affordable, private, home, accommodation 
##       FREX: housing, tenants, rented, tenancies, homelessness, leasehold, landlords 
##       Lift: one-for-one, one-bedroom, rented, right-to-buy, #19, #21.5, #28.5 
##       Score: housing, homes, tenants, rented, rent, landlords, affordable 
## Topic 44 Top Words:
##       Highest Prob: question, order, mr, put, asked, answer, questions 
##       FREX: question, answer, questions, speaker, asked, deputy, answers 
##       Lift: 11.00, 11.57, 12.26, 1223, 1232, 1412, 1555-56 
##       Score: question, speaker, mr, answer, deputy, order, questions 
## Topic 45 Top Words:
##       Highest Prob: research, cancer, treatment, medical, condition, screening, disease 
##       FREX: embryos, prostate, cervical, hepatitis, cloning, transplant, embryo 
##       Lift: abnormalities, cystic, embryo, fertilisation, marrow, @cfaware, #500 
##       Score: cancer, patients, embryos, screening, treatment, tissue, breast 
## Topic 46 Top Words:
##       Highest Prob: online, internet, farmers, animals, digital, animal, broadband 
##       FREX: cull, badgers, badger, fur, bovine, mink, culling 
##       Lift: culling, @daisydumble, @donna_smiley, @jimspin, @leamingtonsbc, @maggieannehayes, @nhconsortium 
##       Score: farmers, animals, internet, cull, animal, online, badgers 
## Topic 47 Top Words:
##       Highest Prob: defence, forces, armed, plymouth, personnel, service, military 
##       FREX: mod, naval, hms, submarines, dockyard, veterans, armed 
##       Lift: hms, submarine, submarines, 1,000-people, 1,625, 1,705, 10-3 
##       Score: defence, armed, forces, plymouth, military, personnel, mod 
## Topic 48 Top Words:
##       Highest Prob: information, home, security, data, immigration, control, orders 
##       FREX: extradition, tpims, sia, warrant, detention, checks, tpim 
##       Lift: carlile's, carlile, sia, 10-month, 10,410, 10,500-for, 10.45 
##       Score: immigration, terrorism, detention, terrorist, tpims, home, security 
## Topic 49 Top Words:
##       Highest Prob: police, officers, crime, policing, home, force, service 
##       FREX: constable, constables, officers, policing, police, soca, ipcc 
##       Lift: 2003-morecambe, 9,650, a19s, ashleys, bigg, bounties, ckp 
##       Score: police, officers, policing, crime, forces, constable, neighbourhood 
## Topic 50 Top Words:
##       Highest Prob: nhs, hospital, patients, health, services, hospitals, care 
##       FREX: dentists, dentistry, pharmacies, pct, nhs, hospitals, hospital 
##       Lift: acos, bequest, bernstein, bodmin, catto, cayton, chailey 
##       Score: nhs, patients, hospital, health, patient, hospitals, care 
## Topic 51 Top Words:
##       Highest Prob: tax, budget, cut, chancellor, cuts, rate, income 
##       FREX: 50p, vat, millionaires, hit, tax, allowances, credits 
##       Lift: #840, 0.76p, 1,003, 1,009, 1,226, 1,275, 1,296 
##       Score: tax, vat, budget, credits, chancellor, cuts, income 
## Topic 52 Top Words:
##       Highest Prob: years, now, two, time, first, three, past 
##       FREX: years, three, months, ago, two, past, weeks 
##       Lift: 10-week-old, 10,616, 11-month, 11-point, 1758, 196b, 63,500 
##       Score: years, months, two, ago, three, past, weeks 
## Topic 53 Top Words:
##       Highest Prob: staff, doctors, emergency, medical, service, training, nurses 
##       FREX: ambulance, junior, staffing, doctors, halifax, posts, nurses 
##       Lift: #i'm, 03, 1-who, 1,454, 1,631, 10,000-strong, 10,000-with 
##       Score: staff, doctors, ambulance, nurses, medical, emergency, junior 
## Topic 54 Top Words:
##       Highest Prob: bill, legislation, act, law, rights, provisions, powers 
##       FREX: bill, legislation, bill's, provisions, passage, regulations, legislative 
##       Lift: 1865, 1990s-when, 1998-it, 19may2000, 2003-largely, 2005-have, 29-year 
##       Score: bill, legislation, provisions, rights, law, powers, regulations 
## Topic 55 Top Words:
##       Highest Prob: public, sector, private, organisations, service, voluntary, services 
##       FREX: public, voluntary, organisations, sector, private, co-operative, volunteering 
##       Lift: 1844, af, carpetbaggers, nebulous, puk, 1075, 170-year 
##       Score: public, sector, private, voluntary, organisations, service, services 
## Topic 56 Top Words:
##       Highest Prob: health, national, inequalities, programme, suicide, disease, department 
##       FREX: flu, hiv, pandemic, inequalities, infections, suicide, mortality 
##       Lift: kirkley, lowestoft, nihr, acupuncture, influenza, #148, #3.6 
##       Score: health, vaccine, flu, inequalities, hiv, infection, suicide 
## Topic 57 Top Words:
##       Highest Prob: council, london, areas, city, area, constituency, centre 
##       FREX: county, mayor, borough, cities, liverpool, city, regeneration 
##       Lift: #12,000, #14.4, #356, #38, #5,000, #500,000, #66.6 
##       Score: london, council, city, regeneration, county, rural, borough 
## Topic 58 Top Words:
##       Highest Prob: advice, legal, cases, civil, hull, aid, case 
##       FREX: hull, tribunal, legal, compensation, solicitors, advice, concentrix 
##       Lift: 0300, 1,997, 1.148, 1.4m, 112.8, 1147, 128,687 
##       Score: legal, advice, hull, aid, compensation, civil, tribunal 
## Topic 59 Top Words:
##       Highest Prob: people, work, many, young, get, people's, can 
##       FREX: people, people's, get, getting, work, young, jobcentre 
##       Lift: 2,425, 294,488, 3,699, 37,290, 5,320, 50-to-64, 75589 
##       Score: people, young, work, get, youth, many, people's 
## Topic 60 Top Words:
##       Highest Prob: tax, revenue, relief, duty, uk, avoidance, hmrc 
##       FREX: evasion, hmrc, gaar, avoidance, inland, stamp, revenue 
##       Lift: 1,643, 3.12, 32.2, 44a, 80g, aaronson, aat 
##       Score: tax, hmrc, avoidance, revenue, relief, evasion, territories 
## Topic 61 Top Words:
##       Highest Prob: government, government's, policy, labour, previous, scotland, scottish 
##       FREX: government, previous, policy, government's, scotland, coalition, scottish 
##       Lift: 2005-perhaps, 80994, actually-that, agency-when, agenda-access, alloway, aware-in 
##       Score: government, scotland, scottish, labour, policy, government's, previous 
## Topic 62 Top Words:
##       Highest Prob: trafficking, home, uk, asylum, refugees, immigration, country 
##       FREX: trafficking, slavery, trafficked, sierra, leone, slave, dubs 
##       Lift: #7, 0.025, 1-yes, 1,060, 1,483, 1,746, 1.123 
##       Score: trafficking, refugees, asylum, slavery, trafficked, immigration, sierra 
## Topic 63 Top Words:
##       Highest Prob: food, products, industry, smoking, advertising, tobacco, ban 
##       FREX: gambling, betting, sunbed, tobacco, cocoa, meat, supermarkets 
##       Lift: 0.7p, 00, 0157, 1,000-almost, 1,032, 1,200-i, 1,666 
##       Score: food, smoking, products, tobacco, advertising, gambling, industry 
## Topic 64 Top Words:
##       Highest Prob: members, debate, many, issues, also, today, heard 
##       FREX: members, debate, heard, speak, sides, issues, hear 
##       Lift: noakes, 6.47pm, accept-or, analysis-but, aspect-listening-is, bunfight, called-making 
##       Score: members, debate, issues, many, opposition, heard, constituents 
## Topic 65 Top Words:
##       Highest Prob: children, child, parents, young, children's, family, contact 
##       FREX: csa, adopters, adoption, child's, cafcass, looked-after, children's 
##       Lift: csa, @mandatenow, 10-month-old, 10-went, 12j, 150765, 16-only 
##       Score: children, child, parents, young, children's, adoption, child's 
## Topic 66 Top Words:
##       Highest Prob: transport, rail, bus, services, line, travel, train 
##       FREX: rail, passengers, passenger, heathrow, hs2, freight, high-speed 
##       Lift: 12-car, 15.15, 50.1, adtranz, anti-icing, bahn, chilterns 
##       Score: rail, transport, bus, passengers, fares, trains, hs2 
## Topic 67 Top Words:
##       Highest Prob: year, million, number, increase, figures, increased, billion 
##       FREX: million, figures, figure, increased, increase, compared, year 
##       Lift: #112, #3,850, #84.3, #87.2, 1,249, 102269, 122.9 
##       Score: million, year, billion, increase, figures, average, increased 
## Topic 68 Top Words:
##       Highest Prob: support, ensure, can, help, aware, taking, take 
##       FREX: aware, ensure, support, taking, steps, continue, help 
##       Lift: 103684, 103965, 107320, 111532, 112584, 113698, 117890 
##       Score: support, ensure, steps, aware, help, taking, department 
## Topic 69 Top Words:
##       Highest Prob: deal, recently, new, can, lack, great, concern 
##       FREX: deal, recently, lack, elsewhere, concern, great, improved 
##       Lift: 2004-a, 721,000, added-gva-per, age-of, centres-jacs-which, employment-can, index-the 
##       Score: deal, recently, new, worktrack, lack, can, great

3.5 Full topic model estimate summary - K69

## 
## Call:
## estimateEffect(formula = 1:69 ~ short_list, stmobj = topic_model2, 
##     metadata = lab_corpus_fem_stm$meta, uncertainty = "Global")
## 
## 
## Topic 1:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0170435  0.0002879   59.20 <0.0000000000000002 ***
## short_listTRUE 0.0069026  0.0003496   19.75 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 2:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0058955  0.0002420  24.358 <0.0000000000000002 ***
## short_listTRUE 0.0007062  0.0003050   2.315              0.0206 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 3:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0087144  0.0001127  77.309 <0.0000000000000002 ***
## short_listTRUE 0.0002131  0.0001475   1.445               0.148    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 4:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0064743  0.0003071   21.08 <0.0000000000000002 ***
## short_listTRUE 0.0036202  0.0003918    9.24 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 5:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0120624  0.0002519   47.88 <0.0000000000000002 ***
## short_listTRUE 0.0035421  0.0003303   10.72 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 6:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0313831  0.0004291   73.14 <0.0000000000000002 ***
## short_listTRUE -0.0093831  0.0004957  -18.93 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 7:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0081985  0.0003833  21.390 < 0.0000000000000002 ***
## short_listTRUE 0.0024229  0.0004801   5.047           0.00000045 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 8:
## 
## Coefficients:
##                  Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)     0.0155977  0.0001354 115.222 < 0.0000000000000002 ***
## short_listTRUE -0.0006674  0.0001470  -4.542           0.00000559 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 9:
## 
## Coefficients:
##                  Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)     0.0106919  0.0002692  39.718 < 0.0000000000000002 ***
## short_listTRUE -0.0025219  0.0003483  -7.241     0.00000000000045 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 10:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0147989  0.0004500  32.885 <0.0000000000000002 ***
## short_listTRUE 0.0002626  0.0005572   0.471               0.637    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 11:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0131078  0.0004357  30.084 <0.0000000000000002 ***
## short_listTRUE -0.0009014  0.0005203  -1.733              0.0832 .  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 12:
## 
## Coefficients:
##                  Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)     0.0100322  0.0003276   30.62 < 0.0000000000000002 ***
## short_listTRUE -0.0026446  0.0003762   -7.03     0.00000000000208 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 13:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0084706  0.0002257  37.532 < 0.0000000000000002 ***
## short_listTRUE 0.0015075  0.0002922   5.159          0.000000249 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 14:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0133846  0.0004574   29.26 <0.0000000000000002 ***
## short_listTRUE 0.0060865  0.0005480   11.11 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 15:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0169555  0.0004249  39.905 < 0.0000000000000002 ***
## short_listTRUE 0.0029760  0.0005174   5.752        0.00000000883 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 16:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0135136  0.0005241  25.786 < 0.0000000000000002 ***
## short_listTRUE 0.0032587  0.0006744   4.832           0.00000135 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 17:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0425046  0.0003183 133.546 <0.0000000000000002 ***
## short_listTRUE 0.0008147  0.0003910   2.084              0.0372 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 18:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0268609  0.0004991   53.82 <0.0000000000000002 ***
## short_listTRUE -0.0068311  0.0006006  -11.37 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 19:
## 
## Coefficients:
##                  Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)     0.0129066  0.0003249  39.726 < 0.0000000000000002 ***
## short_listTRUE -0.0016947  0.0003861  -4.389            0.0000114 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 20:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0086065  0.0003458   24.89 <0.0000000000000002 ***
## short_listTRUE 0.0060669  0.0004429   13.70 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 21:
## 
## Coefficients:
##                  Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)     0.0124514  0.0003124  39.855 < 0.0000000000000002 ***
## short_listTRUE -0.0011159  0.0003980  -2.804              0.00505 ** 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 22:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0127297  0.0003157  40.326 <0.0000000000000002 ***
## short_listTRUE 0.0008318  0.0003993   2.083              0.0372 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 23:
## 
## Coefficients:
##                  Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)     0.0185756  0.0005551  33.463 < 0.0000000000000002 ***
## short_listTRUE -0.0027946  0.0006233  -4.484           0.00000735 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 24:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0138603  0.0002290  60.516 < 0.0000000000000002 ***
## short_listTRUE 0.0013402  0.0002851   4.702           0.00000259 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 25:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0111248  0.0001346  82.653 < 0.0000000000000002 ***
## short_listTRUE 0.0007890  0.0001684   4.686           0.00000279 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 26:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0098015  0.0002871   34.14 <0.0000000000000002 ***
## short_listTRUE 0.0037726  0.0003834    9.84 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 27:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0103138  0.0002167  47.587 < 0.0000000000000002 ***
## short_listTRUE 0.0009108  0.0002731   3.335             0.000852 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 28:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0111592  0.0004003  27.877 < 0.0000000000000002 ***
## short_listTRUE 0.0028078  0.0005067   5.541         0.0000000302 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 29:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0105108  0.0003591  29.266 <0.0000000000000002 ***
## short_listTRUE 0.0042226  0.0004472   9.442 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 30:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0169430  0.0004391   38.59 <0.0000000000000002 ***
## short_listTRUE 0.0007979  0.0005542    1.44                0.15    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 31:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0369173  0.0002220   166.3 <0.0000000000000002 ***
## short_listTRUE -0.0068129  0.0002827   -24.1 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 32:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0100393  0.0001339  74.960 <0.0000000000000002 ***
## short_listTRUE -0.0002587  0.0001601  -1.616               0.106    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 33:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0230283  0.0005077   45.36 <0.0000000000000002 ***
## short_listTRUE -0.0059535  0.0006388   -9.32 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 34:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0136827  0.0004462  30.662 <0.0000000000000002 ***
## short_listTRUE 0.0010979  0.0005552   1.978               0.048 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 35:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0198285  0.0003381   58.65 <0.0000000000000002 ***
## short_listTRUE -0.0061414  0.0003909  -15.71 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 36:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0061167  0.0003208   19.07 <0.0000000000000002 ***
## short_listTRUE 0.0041061  0.0004083   10.06 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 37:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0069657  0.0003196  21.794 < 0.0000000000000002 ***
## short_listTRUE 0.0015000  0.0004215   3.558             0.000373 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 38:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0226435  0.0005276   42.92 <0.0000000000000002 ***
## short_listTRUE -0.0073560  0.0006033  -12.19 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 39:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0205479  0.0006330  32.459 <0.0000000000000002 ***
## short_listTRUE 0.0011686  0.0008248   1.417               0.157    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 40:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0139287  0.0003563   39.09 <0.0000000000000002 ***
## short_listTRUE 0.0047449  0.0004501   10.54 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 41:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0107933  0.0001173   92.02 <0.0000000000000002 ***
## short_listTRUE -0.0014800  0.0001338  -11.06 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 42:
## 
## Coefficients:
##                  Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)     0.0150546  0.0004394  34.258 < 0.0000000000000002 ***
## short_listTRUE -0.0033632  0.0005466  -6.153       0.000000000766 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 43:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0140285  0.0004847  28.944 < 0.0000000000000002 ***
## short_listTRUE 0.0021713  0.0006060   3.583              0.00034 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 44:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0147160  0.0002666  55.195 < 0.0000000000000002 ***
## short_listTRUE 0.0016371  0.0003344   4.896          0.000000981 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 45:
## 
## Coefficients:
##                  Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)     0.0135446  0.0004531  29.893 < 0.0000000000000002 ***
## short_listTRUE -0.0036865  0.0005326  -6.922     0.00000000000448 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 46:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0067864  0.0003654   18.57 <0.0000000000000002 ***
## short_listTRUE 0.0042905  0.0004437    9.67 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 47:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0077671  0.0003507   22.14 < 0.0000000000000002 ***
## short_listTRUE 0.0027525  0.0004454    6.18       0.000000000644 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 48:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0225033  0.0005094   44.17 <0.0000000000000002 ***
## short_listTRUE -0.0077118  0.0005846  -13.19 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 49:
## 
## Coefficients:
##                  Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)     0.0155770  0.0004835  32.215 < 0.0000000000000002 ***
## short_listTRUE -0.0038810  0.0005926  -6.549      0.0000000000582 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 50:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0232448  0.0006509   35.71 <0.0000000000000002 ***
## short_listTRUE -0.0076653  0.0007471  -10.26 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 51:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0105760  0.0003567   29.65 <0.0000000000000002 ***
## short_listTRUE 0.0055916  0.0004514   12.39 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 52:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.01749013 0.00018623  93.915 <0.0000000000000002 ***
## short_listTRUE 0.00001905 0.00022924   0.083               0.934    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 53:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0107598  0.0003976  27.063 <0.0000000000000002 ***
## short_listTRUE 0.0003065  0.0004669   0.657               0.511    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 54:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0261048  0.0004279  61.000 <0.0000000000000002 ***
## short_listTRUE -0.0044993  0.0004925  -9.135 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 55:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0101880  0.0001856  54.899 <0.0000000000000002 ***
## short_listTRUE -0.0004804  0.0002437  -1.972              0.0487 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 56:
## 
## Coefficients:
##                  Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)     0.0114035  0.0003502  32.563 < 0.0000000000000002 ***
## short_listTRUE -0.0015375  0.0004365  -3.522             0.000428 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 57:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0129069  0.0003207  40.243 < 0.0000000000000002 ***
## short_listTRUE 0.0012919  0.0004120   3.136              0.00172 ** 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 58:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0090850  0.0002448  37.113 < 0.0000000000000002 ***
## short_listTRUE 0.0015904  0.0003330   4.775            0.0000018 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 59:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0166458  0.0001923  86.552 < 0.0000000000000002 ***
## short_listTRUE 0.0007301  0.0002314   3.155              0.00161 ** 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 60:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0100660  0.0003752  26.831 <0.0000000000000002 ***
## short_listTRUE -0.0002233  0.0004601  -0.485               0.628    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 61:
## 
## Coefficients:
##                 Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)    0.0112650  0.0001136   99.15 <0.0000000000000002 ***
## short_listTRUE 0.0019039  0.0001402   13.58 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 62:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0104588  0.0003939  26.554 <0.0000000000000002 ***
## short_listTRUE -0.0010404  0.0004713  -2.208              0.0273 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 63:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0088039  0.0003593  24.500 < 0.0000000000000002 ***
## short_listTRUE 0.0020095  0.0004632   4.338            0.0000144 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 64:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0207843  0.0002282  91.080 < 0.0000000000000002 ***
## short_listTRUE 0.0017465  0.0003042   5.742        0.00000000942 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 65:
## 
## Coefficients:
##                  Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)     0.0136841  0.0003857  35.481 < 0.0000000000000002 ***
## short_listTRUE -0.0017372  0.0004613  -3.766             0.000166 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 66:
## 
## Coefficients:
##                 Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)    0.0132102  0.0004836  27.317 < 0.0000000000000002 ***
## short_listTRUE 0.0037765  0.0005855   6.451       0.000000000112 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 67:
## 
## Coefficients:
##                  Estimate Std. Error t value             Pr(>|t|)    
## (Intercept)     0.0219813  0.0003095  71.033 < 0.0000000000000002 ***
## short_listTRUE -0.0011535  0.0003847  -2.999              0.00271 ** 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 68:
## 
## Coefficients:
##                  Estimate Std. Error t value            Pr(>|t|)    
## (Intercept)     0.0193964  0.0001788   108.5 <0.0000000000000002 ***
## short_listTRUE -0.0026870  0.0002297   -11.7 <0.0000000000000002 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## 
## Topic 69:
## 
## Coefficients:
##                   Estimate  Std. Error t value            Pr(>|t|)    
## (Intercept)     0.00275135  0.00001988 138.408 <0.0000000000000002 ***
## short_listTRUE -0.00002552  0.00002595  -0.983               0.325    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1